Activity modelling and unusual event detection in a network of cameras is challenging particularly when the camera views are not overlapped. We show that it is possible to detect u...
Camera motion detection is essential for automated video analysis. We propose a new probabilistic model for detecting zoom-in/zoom-out operations. The model uses EM to estimate th...
: This paper investigates a direct Target Motion Analysis (TMA) estimator for the problem of calculating the states (i.e. source positions, velocities, etc.) of multiple sources fr...
Reconstruction-based super-resolution from motion video has been an active area of study in computer vision and video analysis. Image alignment is a key component of super-resoluti...
In this paper we present a novel approach using a 4D (x,y,z,t) action feature model (4D-AFM) for recognizing actions from arbitrary views. The 4D-AFM elegantly encodes shape and m...